# LLM Security Plugin for Claude Code

> A Claude Code plugin that scans, audits and threat-models agentic AI projects. It layers runtime hooks that block, deterministic Node.js scanners that compute, and advisory `/security` slash-commands that judge, mapped to OWASP LLM Top 10, OWASP Agentic AI Top 10, OWASP Skills Top 10, MCP Top 10, and the DeepMind AI Agent Traps taxonomy.

This file exists for an AI agent already standing in this repository that needs
one deterministic place to find what this artifact is and how it is started.
It cites `README.md`; it does not replace it.

Install — verbatim from the first code block in `README.md`:

```bash
claude plugin marketplace add https://git.fromaitochitta.com/open/ktg-plugin-marketplace.git
claude plugin install llm-security@ktg-plugin-marketplace
```

Then run `/security` in Claude Code for the command router, or `/security posture`
for a first scorecard.

## Docs

- [README.md](README.md): what the plugin is, install, every command, known limitations, non-goals
- [CLAUDE.md](CLAUDE.md): the plugin's own operating instructions — commands, hooks, agents, security boundaries
- [SECURITY.md](SECURITY.md): supported versions, deprecation notice period, how to report a vulnerability
- [CHANGELOG.md](CHANGELOG.md): every release, newest first
- [CONTRIBUTING.md](CONTRIBUTING.md): the fork-and-own model — issues are signals, pull requests are not accepted

## Optional

- [docs/scanner-reference.md](docs/scanner-reference.md): scanner internals, CLI surface, CI/CD templates, knowledge files
- [docs/defense-philosophy.md](docs/defense-philosophy.md): why the three layers are independent, and what none of them catch
- [docs/version-history.md](docs/version-history.md): release notes from v7.0.0 onward